INDEX

Explanations

liner

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

layer

-0.28

rolled

-0.27

.creator

-0.26

ä¸įçĶĺ

-0.25

 impressions

-0.25

ä¸Ģé¡¿

-0.25

åįıè°ĥ

-0.24

roid

-0.24

coords

-0.24

:(

-0.24

POSITIVE LOGITS

infinity

0.29

 Bewert

0.28

assin

0.28

encing

0.28

äº¡

0.27

alten

0.26

èĳ£

0.25

Ø¨Ø±ÙĬ

0.24

zug

0.24

iss

0.23

Activations Density 0.050%

liner

No Comments

No Known Activations